- 11 6月, 2019 1 次提交
-
-
由 Ross Wightman 提交于
Default to img_size in model default_cfg, defer output folder creation until later in the init sequence
-
- 08 6月, 2019 1 次提交
-
-
由 Ross Wightman 提交于
* ModelEma class added to track an EMA set of weights for the model being trained * EMA handling added to train, validation and clean_checkpoint scripts * Add multi checkpoint or multi-model validation support to validate.py * Add syncbn option (APEX) to train script for experimentation * Cleanup interface of CheckpointSaver while adding ema functionality
-
- 01 6月, 2019 2 次提交
-
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
- 31 5月, 2019 2 次提交
-
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
* B0-B3 weights ported from TF with close to paper accuracy * Renamed gen_mobilenet to gen_efficientnet since scaling params go well beyond 'mobile' specific * Add Tensorflow preprocessing option for closer images to source repo
-
- 30 5月, 2019 3 次提交
-
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
Add EfficientNet impl, change existing depth_multipler -> channel_multiplier as definitions have been confused
-
- 29 5月, 2019 2 次提交
-
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
- 27 5月, 2019 3 次提交
-
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
Fix bug for prefetcher
-
- 26 5月, 2019 1 次提交
-
-
由 Zhun Zhong 提交于
Set input and target to Cuda when without using prefetcher.
-
- 24 5月, 2019 3 次提交
-
-
由 Ross Wightman 提交于
Update header comment
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
- 21 5月, 2019 3 次提交
-
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
- 19 5月, 2019 3 次提交
-
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
* Do mixup in custom collate fn if prefetcher enabled, reduces performance impact * Move mixup code to own file * Add arg to disable prefetcher * Fix no cuda transfer when prefetcher off * Random erasing when prefetcher off wasn't changed to match new args, fixed * Default random erasing to off (prob = 0.) for train
-
由 Ross Wightman 提交于
-
- 17 5月, 2019 1 次提交
-
-
由 Ross Wightman 提交于
* factor out data related constants to own file * move data related config helpers to own file * add a variant of RandomResizeCrop that randomizes interpolation method * remove old Numpy version of RandomErasing * cleanup torch version of RandomErasing and use it in either GPU loader batch mode or single image cpu Transform
-
- 16 5月, 2019 1 次提交
-
-
由 Ross Wightman 提交于
-
- 15 5月, 2019 3 次提交
-
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
* init square_avg with one instead of zero as per TF * match TF order of ops for square_avg accumulation * move LR scaling to momentum buffer accumulator as per TF * add decoupled weight decay flag (not in TF)
-
由 Ross Wightman 提交于
-
- 14 5月, 2019 3 次提交
-
-
由 Ross Wightman 提交于
Identity is not the same thing as equality in Python
-
由 cclauss 提交于
Identity is not the same thing as equality in Python. In these instances, we want the latter. Use ==/!= to compare str, bytes, and int literals. $ __python__ ```python >>> proj = "pro" >>> proj += 'j' >>> proj 'proj' >>> proj == 'proj' True >>> proj is 'proj' False >>> 0 == 0.0 True >>> 0 is 0.0 False ``` [flake8](http://flake8.pycqa.org) testing of https://github.com/rwightman/pytorch-image-models on Python 3.7.1 $ __flake8 . --count --select=E9,F63,F72,F82 --show-source --statistics__ ``` ./data/loader.py:48:23: F823 local variable 'input' defined as a builtin referenced before assignment yield input, target ^ ./models/dpn.py:170:12: F632 use ==/!= to compare str, bytes, and int literals if block_type is 'proj': ^ ./models/dpn.py:173:14: F632 use ==/!= to compare str, bytes, and int literals elif block_type is 'down': ^ ./models/dpn.py:177:20: F632 use ==/!= to compare str, bytes, and int literals assert block_type is 'normal' ^ 3 F632 use ==/!= to compare str, bytes, and int literals 1 F823 local variable 'input' defined as a builtin referenced before assignment 4 ``` __E901,E999,F821,F822,F823__ are the "_showstopper_" [flake8](http://flake8.pycqa.org) issues that can halt the runtime with a SyntaxError, NameError, etc. These 5 are different from most other flake8 issues which are merely "style violations" -- useful for readability but they do not effect runtime safety. * F821: undefined name `name` * F822: undefined name `name` in `__all__` * F823: local variable name referenced before assignment * E901: SyntaxError or IndentationError * E999: SyntaxError -- failed to compile a file into an Abstract Syntax Tree
-
由 Ross Wightman 提交于
* initial impl w/ label smoothing converging, but needs more testing
-
- 12 5月, 2019 2 次提交
-
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
* fix expansion ratio on early block * change comment re stride mistake in paper * fix rounding not being called properly for all multipliers != 1.0
-
- 11 5月, 2019 2 次提交
-
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
- 29 4月, 2019 3 次提交
-
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
Add notes for latest mobile model weights...
-
由 Ross Wightman 提交于
Add support for tflite mnasnet pretrained weights and included spnasnet pretrained weights of my own. * tensorflow 'SAME' padding support added to GenMobileNet models for tflite pretrained weights * folded batch norm support (made batch norm optional and enable conv bias) for tflite pretrained weights * add url for spnasnet1_00 weights that I recently trained * fix SE reduction size for semnasnet models
-
- 23 4月, 2019 1 次提交
-
-
由 Ross Wightman 提交于
-